Import

import pandas as pd
import numpy as np
import os


from itertools import takewhile, dropwhile
from collections import Counter

import plotly.express as px
import plotly.graph_objects as go
from plotly.subplots import make_subplots

import dataframes_util as ut

Import base df

if (not os.path.isfile('../tweets.csv')):
    %run userPreparation.ipynb

dfPosts = pd.read_csv('../tweets.csv',low_memory=False)

dfPosts

	id	id_str	created_at	user_id	user_screen_name	user_verified	user_created_at	text	source	coordinates	...	user_tweets_count	user_friends_count	user_followers_count	user_code_error	rt_user_code_error	in_reply_to_user_code_error	is_self_rt	user_url_cred	rt_user_url_cred	in_reply_to_user_url_cred
0	1311804409903484930	1311804409903484930	Thu Oct 01 23:05:18 +0000 2020	1035959506700783618	alessia_smile6	False	Sat Sep 01 18:36:08 +0000 2018	Altri tre giorni di blocco per aver citato un ...	<a href="http://twitter.com/download/android" ...	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	False	NaN	NaN	NaN
1	1311813787159130117	1311813787159130117	Thu Oct 01 23:42:33 +0000 2020	113584953	GiornaledPuglia	False	Fri Feb 12 09:11:24 +0000 2010	Covid, vaccino AstraZeneca alla prova dell'Age...	<a href="https://dlvrit.com/" rel="nofollow">d...	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	False	NaN	NaN	NaN
2	1311805637303644161	1311805637303644161	Thu Oct 01 23:10:10 +0000 2020	1279710942020984832	TestPerTutti	False	Sun Jul 05 09:37:48 +0000 2020	https://t.co/oQZpHUBKrt	<a href="http://twitter.com/download/android" ...	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	False	1.00	1.00	NaN
3	1311798617578049538	1311798617578049538	Thu Oct 01 22:42:17 +0000 2020	1215779772762148865	CapitanHarlok6	False	Fri Jan 10 23:37:56 +0000 2020	"Dobbiamo resistere con il coltello tra i dent...	<a href="http://twitter.com/download/iphone" r...	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	False	0.90	NaN	NaN
4	1311806869917388801	1311806869917388801	Thu Oct 01 23:15:04 +0000 2020	2660808424	soteros1	False	Tue Jul 01 17:29:02 +0000 2014	Se volevate sapere perché Burioni viene invita...	<a href="http://twitter.com/download/iphone" r...	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	False	0.62	0.77	NaN
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
4053196	1394609996197937159	1394609996197937159	Tue May 18 11:05:08 +0000 2021	464822421	CiaoGrosso	False	Sun Jan 15 17:25:21 +0000 2012	Il medico testimonial pro vaccino a @Ariacheti...	<a href="http://twitter.com/download/iphone" r...	NaN	...	102577.0	1060.0	1114.0	NaN	NaN	NaN	False	0.33	1.00	NaN
4053197	1394610015823147011	1394610015823147011	Tue May 18 11:05:13 +0000 2021	497188910	Rosskitty77	False	Sun Feb 19 18:26:36 +0000 2012	"...«Ha lividi e piastrine basse». E ha richie...	<a href="https://mobile.twitter.com" rel="nofo...	NaN	...	79297.0	772.0	893.0	NaN	NaN	NaN	False	0.58	NaN	NaN
4053198	1394609887641022464	1394609887641022464	Tue May 18 11:04:42 +0000 2021	955571652468801536	GuidoIafrate	False	Mon Jan 22 22:43:30 +0000 2018	Vaccinazioni nei luoghi di lavoro, fondamental...	<a href="http://twitter.com/download/android" ...	NaN	...	655.0	226.0	55.0	NaN	NaN	NaN	False	NaN	NaN	NaN
4053199	1394609899963830275	1394609899963830275	Tue May 18 11:04:45 +0000 2021	57358236	lucabattanta	False	Thu Jul 16 15:14:03 +0000 2009	A #lariachetira c’è un MEDICO DI BASE che ha a...	<a href="https://mobile.twitter.com" rel="nofo...	NaN	...	517677.0	13671.0	20847.0	NaN	NaN	NaN	False	0.81	0.89	NaN
4053200	1394609930540306433	1394609930540306433	Tue May 18 11:04:52 +0000 2021	3131638209	kyappy80	False	Fri Apr 03 20:02:31 +0000 2015	Battiato detestava lo scientismo. Meglio che n...	<a href="https://mobile.twitter.com" rel="nofo...	NaN	...	6016.0	138.0	68.0	NaN	NaN	NaN	False	NaN	NaN	NaN

4053201 rows × 56 columns

Filtered by retweet

High credibility

listHighCred =  ['tagadala7', 'La7tv', 'Corriere', 'tg2rai', 'TgrRaiPuglia', 'Linkiesta', 'ilfoglio_it', 
                 'fanpage', 'LaStampa', 'RaiNews', 'fattoquotidiano', 'TgrRaiVeneto', 'agorarai', 'TgrRaiSicilia', 
                 'UnioneSarda', 'SkyTG24', 'repubblica', 'TgrRai', 'Agenzia_Ansa', 'Tg3web', 'TgrRaiToscana', 
                 'Affaritaliani', 'TgrRaiTrentino', 'PiazzapulitaLA7', 'Adnkronos', 'agerpres', 'RepubblicaTv', 
                 'TgrRaiFVG', 'ilpost', 'Open_gol', 'Radio1Rai', 'MediasetTgcom24', 'TgLa7', 'RaiStudio24', 
                 'TgrRaiMolise', 'sole24ore', 'Ticinonline', 'ricpuglisi', 'SimoneCosimi', 'giusmo1', 'RobertoBurioni',
                 'rtl1025', 'messveneto', 'HuffPostItalia', 'Agenzia_Italia', 'ItaliaViva', 'iltirreno', 'Agenzia_Dire',
                 'stebellentani', 'eziomauro', 'QRepubblica', 'lucianocapone', 'robersperanza', 'vocedelpatriota', 
                 'GiovaQuez', 'Cartabellotta', 'istsupsan', 'christianrocca', 'Zeta_Luiss', 'radioanchio', '24Mattino', 
                 'sottoinchiesta', 'riotta']

Retweeted by an high credibility user

userNovax = listSuspect print('Generation 0') print("\tNumber of users: %d"%len(userNovax)) for i in range(0,1): print('Generation %d'%(i+1)) retweeted = ut.retweeted_by_suspect(dfPosts,userNovax) userNovax = userNovax + list(retweeted.index) userNovax = list(set(userNovax)) print("\tNumber of users: %d"%len(userNovax)) len(userNovax)

Retweet an high credibility user

#Account that have retweeted a suspect (follower)
userHighCred = listHighCred
dfRetweet = pd.DataFrame()
print ("Generation ",0, ": ",len(userHighCred))

for i in range(0, 1):
    dfRetweet = ut.retweet_a_suspect(dfPosts,userHighCred)
    userHighCred = userHighCred + list(dfRetweet[dfRetweet['rt_rate']>=10.0].index)
    userHighCred = list(set(userHighCred))
    print ("Generation ",i+1, ": ",len(userHighCred))
dfRetweet

Generation  0 :  63
Generation  1 :  10832

	total	suspect	rt_rate
user_screen_name
00000o0OOOO00	87	2.0	2.298851
00650301	35	0.0	0.000000
007Vincentxxx	111	9.0	8.108108
009mattiaa	13	8.0	61.538462
00MrFrost00	44	1.0	2.272727
...	...	...	...
zucche_rosa	21	0.0	0.000000
zucchigio	46	2.0	4.347826
zuggy04	246	49.0	19.918699
zxuz53	17	0.0	0.000000
zziocane66	354	0.0	0.000000

29224 rows × 3 columns

fig = px.histogram(x=dfRetweet[dfRetweet['rt_rate']>0]["rt_rate"],
                 histnorm='percent',title="Retweet rate on follower (high credibility)")
fig.update_xaxes(title='retweet rate')
fig.show()

dfProvax = dfPosts[dfPosts.isin(userHighCred)['user_screen_name']].copy()

NoVax

listSuspect = ['IacobellisT','Piero42395724', 'TommyBrain','xenonian1', 'Z3r0Rules','Pietro_Otto',
               'MarySpes','manu_etoile','CarpaneseSilva1','il_brigante07','Sakurauchi_Hime','MinervaMcGrani1',
              'marchesaangeli','lucabattanta',
              'gael99','LPinicia','Mariang47614228','SoniaLaVera','valy_s','Samira1577','daniele19921','d_essere'
              'anto_galli4','LuigiF97101292','EureosCriss','vaniacavi',
              'markred17','RenzoCianchetti','12qbert','ManuQ24916888','bisagnino','thewaterflea',
              'BarbaraRaval','noitre32','intuslegens','pbecchi','miia_2018','ladyonorato','cris_cersei','RadioSavana',
              'lameduck1960','a_meluzzi','francescatotolo','Mr_Ozymandias','FmMosca','LaVeritaWeb','Bluefidel47',
              'fdragoni','byoblu','MinutemanItaly','TarroGiulio','NicolaPorro','25O319','sabrina__sf','liliaragnar',
              'FabioFranchi1','EliseiNicole']

Retweeted by a suspect

Any user that is defined as a novax that retweets a user, the retweeted user will automatically be considered a novax

userNovax = listSuspect print('Generation 0') print("\tNumber of users: %d"%len(userNovax)) for i in range(0,1): print('Generation %d'%(i+1)) retweeted = ut.retweeted_by_suspect(dfPosts,userNovax) userNovax = userNovax + list(retweeted.index) userNovax = list(set(userNovax)) print("\tNumber of users: %d"%len(userNovax)) len(userNovax)

Retweet a suspect

#Account that have retweeted a suspect (follower)
userNovax = listSuspect
dfRetweet = pd.DataFrame()
print ("Generation ",0, ": ",len(userNovax))
for i in range(0, 2):
    dfRetweet = ut.retweet_a_suspect(dfPosts,userNovax)
    userNovax = userNovax + list(dfRetweet[dfRetweet['rt_rate']>=20.0].index)
    userNovax = list(set(userNovax))
    
    print ("Generation ",i+1, ": ",len(userNovax))

dfRetweet

Generation  0 :  56
Generation  1 :  5730
Generation  2 :  8490

	total	suspect	rt_rate
user_screen_name
00000o0OOOO00	87	38.0	43.678161
00650301	35	1.0	2.857143
007Vincentxxx	111	1.0	0.900901
009mattiaa	13	0.0	0.000000
00MrFrost00	44	0.0	0.000000
...	...	...	...
zucche_rosa	21	2.0	9.523810
zucchigio	46	0.0	0.000000
zuggy04	246	0.0	0.000000
zxuz53	17	7.0	41.176471
zziocane66	354	203.0	57.344633

29224 rows × 3 columns

fig = px.histogram(x=dfRetweet[dfRetweet['rt_rate']>0]["rt_rate"],
                 histnorm='percent',title="Retweet rate on follower (novax)")
fig.update_xaxes(title='retweet rate')
fig.show()

dfNovax = dfPosts[dfPosts.isin(userNovax)['user_screen_name']].copy()

.CSV Creation

Novax

dfNovax.drop_duplicates(['id'],inplace=True)
dfNovax

	id	id_str	created_at	user_id	user_screen_name	user_verified	user_created_at	text	source	coordinates	...	user_tweets_count	user_friends_count	user_followers_count	user_code_error	rt_user_code_error	in_reply_to_user_code_error	is_self_rt	user_url_cred	rt_user_url_cred	in_reply_to_user_url_cred
0	1311804409903484930	1311804409903484930	Thu Oct 01 23:05:18 +0000 2020	1035959506700783618	alessia_smile6	False	Sat Sep 01 18:36:08 +0000 2018	Altri tre giorni di blocco per aver citato un ...	<a href="http://twitter.com/download/android" ...	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	False	NaN	NaN	NaN
4	1311806869917388801	1311806869917388801	Thu Oct 01 23:15:04 +0000 2020	2660808424	soteros1	False	Tue Jul 01 17:29:02 +0000 2014	Se volevate sapere perché Burioni viene invita...	<a href="http://twitter.com/download/iphone" r...	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	False	0.62	0.77	NaN
6	1311808100773629953	1311808100773629953	Thu Oct 01 23:19:58 +0000 2020	975616683611181057	Fedoraquattroc2	False	Mon Mar 19 06:15:18 +0000 2018	@ValeMameli Serve una svolta rapida da questa ...	<a href="http://twitter.com/download/android" ...	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	False	0.37	NaN	0.95
8	1311807149379551238	1311807149379551238	Thu Oct 01 23:16:11 +0000 2020	31553996	F52	False	Wed Apr 15 23:07:10 +0000 2009	Altri tre giorni di blocco per aver citato un ...	<a href="http://twitter.com/download/android" ...	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	False	NaN	NaN	NaN
9	1311804362440794113	1311804362440794113	Thu Oct 01 23:05:06 +0000 2020	1094614208107499520	laura_pi79	False	Sun Feb 10 15:08:58 +0000 2019	Altri tre giorni di blocco per aver citato un ...	<a href="http://twitter.com/download/android" ...	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	False	0.50	NaN	NaN
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
4053195	1394610031262306304	1394610031262306304	Tue May 18 11:05:16 +0000 2021	4309630395	Ileana0406	False	Sat Nov 28 18:18:40 +0000 2015	Vaccini, nuovo errore di somministrazione in T...	<a href="http://twitter.com/download/iphone" r...	NaN	...	21105.0	1130.0	833.0	NaN	NaN	NaN	False	NaN	1.00	NaN
4053196	1394609996197937159	1394609996197937159	Tue May 18 11:05:08 +0000 2021	464822421	CiaoGrosso	False	Sun Jan 15 17:25:21 +0000 2012	Il medico testimonial pro vaccino a @Ariacheti...	<a href="http://twitter.com/download/iphone" r...	NaN	...	102577.0	1060.0	1114.0	NaN	NaN	NaN	False	0.33	1.00	NaN
4053197	1394610015823147011	1394610015823147011	Tue May 18 11:05:13 +0000 2021	497188910	Rosskitty77	False	Sun Feb 19 18:26:36 +0000 2012	"...«Ha lividi e piastrine basse». E ha richie...	<a href="https://mobile.twitter.com" rel="nofo...	NaN	...	79297.0	772.0	893.0	NaN	NaN	NaN	False	0.58	NaN	NaN
4053199	1394609899963830275	1394609899963830275	Tue May 18 11:04:45 +0000 2021	57358236	lucabattanta	False	Thu Jul 16 15:14:03 +0000 2009	A #lariachetira c’è un MEDICO DI BASE che ha a...	<a href="https://mobile.twitter.com" rel="nofo...	NaN	...	517677.0	13671.0	20847.0	NaN	NaN	NaN	False	0.81	0.89	NaN
4053200	1394609930540306433	1394609930540306433	Tue May 18 11:04:52 +0000 2021	3131638209	kyappy80	False	Fri Apr 03 20:02:31 +0000 2015	Battiato detestava lo scientismo. Meglio che n...	<a href="https://mobile.twitter.com" rel="nofo...	NaN	...	6016.0	138.0	68.0	NaN	NaN	NaN	False	NaN	NaN	NaN

1361155 rows × 56 columns

High credibility

dfProvax.drop_duplicates(['id'],inplace=True)
dfProvax

	id	id_str	created_at	user_id	user_screen_name	user_verified	user_created_at	text	source	coordinates	...	user_tweets_count	user_friends_count	user_followers_count	user_code_error	rt_user_code_error	in_reply_to_user_code_error	is_self_rt	user_url_cred	rt_user_url_cred	in_reply_to_user_url_cred
2	1311805637303644161	1311805637303644161	Thu Oct 01 23:10:10 +0000 2020	1279710942020984832	TestPerTutti	False	Sun Jul 05 09:37:48 +0000 2020	https://t.co/oQZpHUBKrt	<a href="http://twitter.com/download/android" ...	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	False	1.00	1.0	NaN
3	1311798617578049538	1311798617578049538	Thu Oct 01 22:42:17 +0000 2020	1215779772762148865	CapitanHarlok6	False	Fri Jan 10 23:37:56 +0000 2020	"Dobbiamo resistere con il coltello tra i dent...	<a href="http://twitter.com/download/iphone" r...	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	False	0.90	NaN	NaN
5	1311806204973404161	1311806204973404161	Thu Oct 01 23:12:26 +0000 2020	607187088	Pattyjune22	False	Wed Jun 13 10:53:22 +0000 2012	Il vaccino contro HPV è sicuro, efficace, grat...	<a href="http://twitter.com/download/android" ...	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	False	NaN	NaN	NaN
17	1311811303078494208	1311811303078494208	Thu Oct 01 23:32:41 +0000 2020	1292021606	FrancyP_	False	Sat Mar 23 17:26:21 +0000 2013	Tamponi e vaccini antinfluenzali devono essere...	<a href="http://twitter.com/download/android" ...	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	False	NaN	NaN	NaN
28	1311802014217707522	1311802014217707522	Thu Oct 01 22:55:46 +0000 2020	1010279700210561025	lantifragile	False	Fri Jun 22 21:53:45 +0000 2018	Il vaccino contro HPV è sicuro, efficace, grat...	<a href="http://twitter.com/download/android" ...	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	False	NaN	NaN	NaN
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
4053174	1394609630542811138	1394609630542811138	Tue May 18 11:03:41 +0000 2021	1402708182	BansCollector	False	Sat May 04 16:15:39 +0000 2013	@stebaraz Quando hai voglia e tempo, che ne pe...	<a href="https://mobile.twitter.com" rel="nofo...	NaN	...	51214.0	1532.0	1087.0	NaN	NaN	NaN	False	NaN	NaN	1.0
4053187	1394609981580840961	1394609981580840961	Tue May 18 11:05:04 +0000 2021	804354408	TgrRai	True	Wed Sep 05 10:56:01 +0000 2012	#vaccino Da oggi possono aderire alla #Campagn...	<a href="https://mobile.twitter.com" rel="nofo...	NaN	...	251546.0	370.0	63681.0	NaN	NaN	NaN	False	1.00	1.0	NaN
4053190	1394609810470055936	1394609810470055936	Tue May 18 11:04:24 +0000 2021	2820333045	OvileItalia	False	Thu Oct 09 19:45:14 +0000 2014	NON C’È VACCINO\n\n#ilmanifesto #laprima del 1...	<a href="http://twitter.com/download/android" ...	NaN	...	21508.0	231.0	190.0	NaN	NaN	NaN	False	0.83	NaN	NaN
4053191	1394609946881298432	1394609946881298432	Tue May 18 11:04:56 +0000 2021	2926782875	Mustapha1508	False	Wed Dec 17 10:59:26 +0000 2014	Vaccino, dopo il caso della 23enne un altro er...	<a href="http://twitter.com/download/iphone" r...	NaN	...	50672.0	5003.0	3923.0	NaN	NaN	NaN	False	NaN	1.0	NaN
4053195	1394610031262306304	1394610031262306304	Tue May 18 11:05:16 +0000 2021	4309630395	Ileana0406	False	Sat Nov 28 18:18:40 +0000 2015	Vaccini, nuovo errore di somministrazione in T...	<a href="http://twitter.com/download/iphone" r...	NaN	...	21105.0	1130.0	833.0	NaN	NaN	NaN	False	NaN	1.0	NaN

872211 rows × 56 columns

Other user

idNovax = dfNovax.groupby('id').first().index
dfOtherElem = dfPosts[dfPosts['id'].isin(idNovax) == False]

idProvax = dfProvax.groupby('id').first().index
dfOtherElem = dfOtherElem[dfOtherElem['id'].isin(idProvax) == False]

dfOtherElem

	id	id_str	created_at	user_id	user_screen_name	user_verified	user_created_at	text	source	coordinates	...	user_tweets_count	user_friends_count	user_followers_count	user_code_error	rt_user_code_error	in_reply_to_user_code_error	is_self_rt	user_url_cred	rt_user_url_cred	in_reply_to_user_url_cred
1	1311813787159130117	1311813787159130117	Thu Oct 01 23:42:33 +0000 2020	113584953	GiornaledPuglia	False	Fri Feb 12 09:11:24 +0000 2010	Covid, vaccino AstraZeneca alla prova dell'Age...	<a href="https://dlvrit.com/" rel="nofollow">d...	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	False	NaN	NaN	NaN
7	1311799458187956228	1311799458187956228	Thu Oct 01 22:45:37 +0000 2020	829427701	Pietroclo_	False	Mon Sep 17 16:57:52 +0000 2012	@mike_fusco Forse la maglia del Napoli è il va...	<a href="http://twitter.com/download/android" ...	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	False	NaN	NaN	NaN
14	1311811293943300096	1311811293943300096	Thu Oct 01 23:32:39 +0000 2020	1118432292131753984	Notiziedi_it	False	Wed Apr 17 08:33:32 +0000 2019	Sanità Roma, l’allarme della farmacista: non a...	<a href="http://publicize.wp.com/" rel="nofoll...	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	False	1.0	NaN	NaN
15	1311813516123398148	1311813516123398148	Thu Oct 01 23:41:29 +0000 2020	72016096	salutedomani	False	Sun Sep 06 11:19:53 +0000 2009	#CORONAVIRUS. #ASTRAZENECA, PARTITA VALUTAZION...	<a href="https://www.google.com/" rel="nofollo...	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	False	NaN	NaN	NaN
16	1311813514479140865	1311813514479140865	Thu Oct 01 23:41:28 +0000 2020	72016096	salutedomani	False	Sun Sep 06 11:19:53 +0000 2009	#CORONAVIRUS. #SANOFI, AL LAVORO SU #VACCINO U...	<a href="https://www.google.com/" rel="nofollo...	NaN	...	NaN	NaN	NaN	NaN	NaN	NaN	False	NaN	NaN	NaN
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
4053184	1394609950278754304	1394609950278754304	Tue May 18 11:04:57 +0000 2021	1339116563950170118	RagDiabolik	False	Wed Dec 16 07:54:15 +0000 2020	@Cartabellotta Rifiutare il vaccino E' UN LEGI...	<a href="https://mobile.twitter.com" rel="nofo...	NaN	...	1440.0	37.0	44.0	NaN	NaN	NaN	False	NaN	NaN	0.97
4053188	1394609936173252610	1394609936173252610	Tue May 18 11:04:54 +0000 2021	767675142	EbenYaakov	False	Sun Aug 19 14:44:25 +0000 2012	@BFMTV @olivierveran Mon corps mon choix , nou...	<a href="https://mobile.twitter.com" rel="nofo...	NaN	...	140023.0	1585.0	1296.0	NaN	NaN	NaN	False	NaN	NaN	NaN
4053189	1394609850089345025	1394609850089345025	Tue May 18 11:04:33 +0000 2021	71210454	tuttoggi	False	Thu Sep 03 09:01:38 +0000 2009	Anche i carabinieri del Nas potrebbero interes...	<a href="https://www.postpickr.com" rel="nofol...	NaN	...	93104.0	228.0	3744.0	NaN	NaN	NaN	False	NaN	NaN	NaN
4053193	1394609894700064771	1394609894700064771	Tue May 18 11:04:44 +0000 2021	171756510	neghittoso	False	Wed Jul 28 02:48:49 +0000 2010	@AndreaBeltrameJ @prokofiev91 @gred_vet @carlo...	<a href="https://mobile.twitter.com" rel="nofo...	NaN	...	11676.0	527.0	280.0	NaN	NaN	NaN	False	NaN	NaN	NaN
4053198	1394609887641022464	1394609887641022464	Tue May 18 11:04:42 +0000 2021	955571652468801536	GuidoIafrate	False	Mon Jan 22 22:43:30 +0000 2018	Vaccinazioni nei luoghi di lavoro, fondamental...	<a href="http://twitter.com/download/android" ...	NaN	...	655.0	226.0	55.0	NaN	NaN	NaN	False	NaN	NaN	NaN

1851775 rows × 56 columns

Write dataframe to .csv

dfProvax.to_csv('retweet_class/tweets_provax.csv', index=False)

dfNovax.to_csv('retweet_class/tweets_novax.csv', index=False)

dfOtherElem.to_csv('retweet_class/tweets_otherUser.csv', index=False)

#Extract to another dataframe info about doubled classified users
doubled_class = list(np.array(dfNovax['user_id'])[pd.Series(dfNovax['user_id']).isin(dfProvax['user_id'])])
dfDoubled = dfPosts[dfPosts['user_id'].isin(doubled_class)]

dfDoubled.to_csv('retweet_class/tweets_doubled_classified.csv', index=False)